04 Jun 2021
09:00 Doctoral defense Fully distance
Theme
Customized Multi-purpose Vehicle Traffic Routing System
Student
Allan Mariano de Souza
Advisor / Teacher
Advisor: Leandro Aparecido Villas / Co-supervisor: Torsten Braun
Brief summary
Vehicle routing is the key to providing better vehicle mobility. However, considering only traffic information to recommend the best routes for each vehicle is far from achieving the desired requirements of a good Traffic Management System (TMS), which aims to improve mobility, driving experience and driver safety. and passengers. In this scenario, context-aware and multi-purpose redirection approaches will play an important role in traffic management, allowing TMSs to consider different urban aspects that can affect route planning decisions, such as mobility, distance, fuel consumption, scenario and security . There are at least three issues that need to be addressed to provide an efficient TMS, including: (i) scalability; (ii) redirection efficiency; and (iii) reliability.
Scalability refers to the system's ability to deliver the desired performance without worrying about the number of vehicles or the size of the scenario. On the other hand, the efficiency of the redirection refers to how good the traffic management of the solution is. Finally, reliability determines how reliable the routes calculated by the system are in relation to future changes in urban dynamics.
In this way, this thesis contributes with efficient and reliable solutions to meet the requirements of future TMSs. The first contribution is in the development of a scalable architecture for traffic management based on distributed and cooperative algorithms to detect the urban environment, estimate urban aspects and redirect vehicles in real time. The second contribution is to enable an efficient multi-objective referral based on the preferences of each user. Thus, each user can determine which urban aspects will be chosen to plan their route. Unlike other multi-purpose approaches, our solution is non-deterministic, which lessens the chance of creating additional congestion points, since vehicles with similar origin and destination will potentially be redirected on different routes. The last contribution of this thesis is to improve the reliability of the routes calculated by the TMSs using a route planning algorithm that considers future changes in the proposed urban dynamics. The main advantage of this solution in relation to the solutions in the literature is that the system predicts future urban dynamics (that is, future changes in traffic conditions, safety risks, etc.); thus, the system knows in advance when some changes will occur and how long they will last, thereby computing more reliable routes.
The proposed solutions were widely compared with other related works in different metrics of performance evaluation.
Examination Board
Headlines:
| Leandro Aparecido Villas | IC / UNICAMP |
| Torsten Braun | Ub |
| Richard Werner Nelem Pazzi | ONTARIOTECH |
| Marília Pascoal Curado | UC |
| Edmundo Roberto Mauro Madeira | IC / UNICAMP |
| Thiago Henrique Silva | IC / UNICAMP |
Substitutes:
| Luiz Fernando Bittencourt | IC / UNICAMP |
| Juliana Freitag Borin | IC / UNICAMP |
| Rafael Lopes Gomes | CCT / UECE |
| Heitor Soares Ramos Filho | DCC / UFMG |